© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 8841
    Prev
    Next
    INDEX
    Explanations

    words related to political processes like "plebiscite" or "referendum."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'b' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OHN
    -0.65
     Angels
    -0.63
    aurus
    -0.63
    orkshire
    -0.62
     Templar
    -0.62
     priceless
    -0.61
     Tanz
    -0.60
    OOD
    -0.59
    ONSORED
    -0.59
     Rack
    -0.59
    POSITIVE LOGITS
    idation
    0.78
    quer
    0.77
    bles
    0.75
    ifix
    0.72
    gency
    0.72
    idian
    0.70
    nic
    0.70
    rences
    0.70
    thal
    0.69
    cit
    0.69
    Activations Density 0.097%

    No Known Activations